© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 48
    Prev
    Next
    INDEX
    Explanations

    say "architecture"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     needle
    -18.25
    .curve
    -16.88
    婴
    -16.75
     Gab
    -16.63
    _uv
    -16.63
     vape
    -16.38
    .cuda
    -16.25
     Lumia
    -16.13
     Nights
    -15.81
    宝妈
    -15.75
    POSITIVE LOGITS
    IDL
    18.25
    国防部
    16.88
    boro
    16.38
    Architecture
    15.63
    DTD
    15.63
    idl
    15.38
    COR
    15.00
    华尔
    15.00
     architecture
    14.50
     IBM
    14.31
    Activations Density 0.157%

    No Known Activations